© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25647
    Prev
    Next
    INDEX
    Explanations

    free poker, marketing budget, my account

    np_acts-logits-general · gemini-2.5-flash-lite

    react to replies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <0xCD>
    0.46
     exquisitely
    0.40
    Brands
    0.40
    Manufact
    0.39
    ›
    0.39
     exquisite
    0.39
    Lond
    0.38
    <0xC8>
    0.38
     ceas
    0.38
    ldquo
    0.37
    POSITIVE LOGITS
    ؟
    0.49
     ؟
    0.49
     আদৌ
    0.48
     ?";
    0.45
     registrazione
    0.44
    ？）
    0.43
    ？
    0.41
     tohoto
    0.41
     रिवीजन
    0.40
     ابھی
    0.40
    Activations Density 0.000%

    No Known Activations